Title :
The Gauss-Newton learning method for a generalized dynamic synapse neural network
Author :
Namarvar, Hassan Heidari ; Dibazar, Alireza A. ; Berger, Theodore W.
Author_Institution :
Dept. of Biomed. Eng., Univ. of Southern California, Los Angeles, CA, USA
fDate :
6/24/1905 12:00:00 AM
Abstract :
A new architecture for dynamic synapse neural networks (DSNNs) has been introduced based on incorporating a continuous nonlinear mechanism to simulate synaptic neuro-transmitter release, adding a nonlinear output layer, and utilizing a Gauss-Newton learning method to train the network. We applied this network to simulate two nonlinear dynamical systems and then identify the dynamical systems by generating random noise observation data. The network estimation error per sample on the training phase was less than approximately 2% and on the test set was less than approximately 3%
Keywords :
feedback; identification; learning (artificial intelligence); neural nets; nonlinear dynamical systems; Gauss Newton learning; cross-feedback architecture; dynamic synapse neural network; nonlinear dynamical systems; random noise; synaptic neural transmitter; system identification; training phase; Estimation error; Learning systems; Least squares methods; Neural networks; Neurotransmitters; Newton method; Noise generators; Nonlinear dynamical systems; Recursive estimation; Testing;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007666
